© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 4854
    Prev
    Next
    INDEX
    Explanations

    numeric patterns or sequences

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ı
    -0.76
    hare
    -0.74
     Nose
    -0.74
     OW
    -0.72
     Doodle
    -0.71
    OW
    -0.71
     Buddy
    -0.70
    odder
    -0.70
    OY
    -0.70
     Yor
    -0.69
    POSITIVE LOGITS
    mission
    0.71
     é
    0.70
    config
    0.68
     63
    0.67
     SEC
    0.67
    ãģ®éŃĶ
    0.66
     province
    0.65
     ])
    0.65
     config
    0.64
    ipl
    0.64
    Activations Density 0.240%

    No Known Activations